© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45593
    Prev
    Next
    INDEX
    Explanations

    Kalman filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ためには
    0.67
    اء
    0.61
     keyring
    0.60
    ために
    0.58
     premiere
    0.57
    ための
    0.56
    ו
    0.55
     ‎
    0.54
    اي
    0.53
    وک
    0.53
    POSITIVE LOGITS
    c
    1.01
    p
    0.99
    df
    0.82
    tumor
    0.77
    critic
    0.70
    detection
    0.68
    dı
    0.67
    k
    0.67
    mf
    0.67
    department
    0.66
    Activations Density 0.000%

    No Known Activations